Probabilistic Pareto plan generation for semiautomated multicriteria radiation therapy treatment planning

  title={Probabilistic Pareto plan generation for semiautomated multicriteria radiation therapy treatment planning},
  author={Tianfang Zhang and Rasmus Bokrantz and Jimmy Olsson},
  journal={Physics in Medicine \& Biology},
Objective. We propose a semiautomatic pipeline for radiation therapy treatment planning, combining ideas from machine learning–automated planning and multicriteria optimization (MCO). Approach. Using knowledge extracted from historically delivered plans, prediction models for spatial dose and dose statistics are trained and furthermore systematically modified to simulate changes in tradeoff priorities, creating a set of differently biased predictions. Based on the predictions, an MCO problem is… 
Predicting scenario doses for robust automated radiation therapy treatment planning
The proposed framework for robust automated treatment planning using machine learning, comprising scenario-specific dose prediction and robust dose mimicking, shows that the predicted scenario doses resemble their respective ground truth well, in particular while having target coverage comparable to that of the nominal scenario.
Robust automated radiation therapy treatment planning using scenario-specific dose prediction and robust dose mimicking.
The feasibility and merits of the proposed methodology for incorporating robustness into automated treatment planning algorithms are demonstrated and it is shown that the predicted scenario doses resemble their respective ground truth well, in particular while having target coverage comparable to that of the nominal scenario.
OpenKBP-Opt: An international and reproducible evaluation of 76 knowledge-based planning pipelines
An open framework for developing plan optimization models for knowledge-based planning (KBP) in radiotherapy and it is demonstrated that the dose mimicking models generated plans that are also optimal for a conventional planning model.


The importance of evaluating the complete automated knowledge-based planning pipeline
  • A. Babier, R. Mahmood, A. McNiven, Adam Diamant, T. Chan
  • Medicine
    Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics
  • 2020
A small number of objective function weight vectors is sufficient for automated treatment planning in prostate cancer.
An automated planning methodology that aims to combine both explorative and prescriptive approaches for improving the efficiency and the quality of the treatment planning process is proposed.
A Novel Machine Learning Model for Dose Prediction in Prostate Volumetric Modulated Arc Therapy Using Output Initialization and Optimization Priorities
A novel machine learning model for predicting the dose distribution for a given patient with a given set of optimization priorities is presented, which may be used for quickly estimating the Pareto set of feasible dose objectives and indirectly improve final plan quality by allowing more time for plan refinement.
Predicting patient specific Pareto fronts from patient anatomy only.
Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future
In this review, the smart planning tools in current clinical use are summarized in 3 main categories: automated rule implementation and reasoning, modeling of prior knowledge in clinical practice, and multicriteria optimization.
Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy.
PURPOSE To demonstrate knowledge-based 3D dose prediction for external beam radiotherapy. METHODS Using previously treated plans as training data, an artificial neural network (ANN) was trained to
Neural network dose models for knowledge‐based planning in pancreatic SBRT
Knowing‐based artificial neural network dose models (ANN‐DMs) to predict dose distributions that would be approved by experienced physicians are developed and accuracy was substantially improved when each physician's treatment approach was taken into account by training their own dedicated models.
A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning
A convolutional deep network model, U-net, is modified for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR) and a desired radiation dose distribution from a patient’s PTV and OAR contours is mapped.
Dosimetric features‐driven machine learning model for DVH prediction in VMAT treatment planning
A novel dosimetric features-driven machine learning model with the use of PTV-only plan has been established for DVH prediction and is capable of efficiently generating best achievable DVHs for VMAT planning.
RapidPlan knowledge based planning: iterative learning process and model ability to steer planning strategies
A refined RP model allowed the generation of plans with improved quality, mostly for parallel organs at risk and, possibly, also the intrinsic model quality.